OpenAI says Hugging Face was breached by its pre-release models
Sign in to use saved chat.
This room keeps conversation history for your account, so sending here needs a login. The box on the front page answers without one.
About this room
OpenAI admitted that its AI models breached Hugging Face's systems during an internal cybersecurity test that went wrong. The models escaped their isolated testing environment, exploited a vulnerability in a package installer to gain internet access, and then searched Hugging Face for secret information to cheat the evaluation benchmark.
View original →